SDXL ControlNet Union

An efficent SDXL multi-controlnet text-to-image model.

Inference$ Commercial useFrom 1 credit per run

About SDXL ControlNet Union

An efficent SDXL multi-controlnet text-to-image model.

diffusioncontrolnetcomposition

Pricing

A run with the default settings costs 1 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextarearequired

The prompt to use for generating the image. Be as descriptive as possible for best results.

controlnet_conditioning_scalenumberdefault: 0.5

The scale of the controlnet conditioning.

negative_prompttextareadefault: ""

The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).

image_sizeselectdefault: null

The size of the generated image. Leave it none to automatically infer from the control image.

Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

num_inference_stepsintegerdefault: 35

The number of inference steps to perform.

seedintegerdefault: null

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

guidance_scalenumberdefault: 7.5

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

sync_modebooleandefault: false

If `True`, the media will be returned as a data URI and the output data won't be available in the request history.

num_imagesintegerdefault: 1

The number of images to generate.

lorasjsondefault: []

The list of LoRA weights to use.

embeddingsjsondefault: []

The list of embeddings to use.

enable_safety_checkerbooleandefault: true

If set to true, the safety checker will be enabled.

safety_checker_versionselectdefault: "v1"

The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.

Options: v1, v2

enable_prompt_expansionbooleandefault: false

If set to true, the prompt will be expanded with additional prompts.

formatselectdefault: "jpeg"

The format of the generated image.

Options: jpeg, png

request_idtextdefault: ""

An id bound to a request, can be used with response to identify the request itself.

openpose_image_urlfiledefault: null

The URL of the control image.

openpose_preprocessbooleandefault: true

Whether to preprocess the openpose image.

depth_image_urlfiledefault: null

The URL of the control image.

depth_preprocessbooleandefault: true

Whether to preprocess the depth image.

teed_image_urlfiledefault: null

The URL of the control image.

teed_preprocessbooleandefault: true

Whether to preprocess the teed image.

canny_image_urlfiledefault: null

The URL of the control image.

canny_preprocessbooleandefault: true

Whether to preprocess the canny image.

normal_image_urlfiledefault: null

The URL of the control image.

normal_preprocessbooleandefault: true

Whether to preprocess the normal image.

segmentation_image_urlfiledefault: null

The URL of the control image.

segmentation_preprocessbooleandefault: true

Whether to preprocess the segmentation image.

More from SDXL ControlNet Union

SDXL ControlNet Union

An efficent SDXL multi-controlnet image-to-image model.

diffusioncontrolnet

image-to-image

SDXL ControlNet Union

An efficent SDXL multi-controlnet inpainting model.

diffusioncontrolnet

image-to-image

Related text to image models

Nano Banana Pro

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

realismtypography

text-to-image

FLUX.1 [schnell]

FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use.

text-to-image

Nano Banana 2

Nano Banana 2 is Google's new state-of-the-art fast image generation and editing model

text-to-image

Nano Banana 2.1

Nano Banana 2.1 by Google generates images from text prompts, with output resolutions up to 4K, adjustable aspect ratios, and optional web search grounding.

image generationphotorealism

text-to-image

GPT Image 2 API

GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.

gpt-image-2openai

text-to-image

GPT Image 2.5 Flare Text to Image

OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds.

realismtypography

text-to-image

FLUX.1 [dev]

FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.

text-to-image

✦ new

GPT Image 2.6 Flare Text to Image

OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds.

realismtypography

text-to-image